{"id":"W2507296351","doi":"10.1007/s11263-018-1140-0","title":"Semantic Understanding of Scenes Through the ADE20K Dataset","year":2018,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1667,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Samsung; National Science Foundation","keywords":"Computer science; Normalization (sociology); Parsing; Segmentation; Artificial intelligence; Variety (cybernetics); Object (grammar); Pixel; Context (archaeology); Pattern recognition (psychology); Computer vision; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004487105,0.004309334,0.001454943,0.004110666,0.0008288556,0.002085818,0.002393354,0.002402711,0.0128831],"category_scores_gemma":[0.001702463,0.0005243616,0.002138079,0.003410436,0.0005446159,0.002532556,0.001545845,0.001648593,0.01099469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001681675,"about_ca_system_score_gemma":0.001506091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03991338,"about_ca_topic_score_gemma":0.0799755,"domain_scores_codex":[0.9991145,0.00007695871,0.00005919251,0.0003651354,0.0002533942,0.0001308085],"domain_scores_gemma":[0.9995666,0.00006773281,0.0000304292,0.0001510258,0.0001268714,0.00005732642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001735485,0.001293821,0.007405235,0.003696461,0.0008449188,0.001158096,0.0002711467,0.01298612,0.02483464,0.003158521,0.7082,0.2344156],"study_design_scores_gemma":[0.0006700928,0.0005461809,0.04573739,0.001088646,0.0007529042,0.002607824,0.001525123,0.104097,0.03767562,0.0131688,0.7917585,0.0003719289],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.08247661,0.007634152,0.01837879,0.0008708907,0.0006463592,0.0007029025,0.8330284,0.03573768,0.02052428],"genre_scores_gemma":[0.04703245,0.0009659543,0.0204709,0.0001895037,0.00005349644,0.0001902694,0.9266271,0.0005049934,0.003965287],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03991338,"threshold_uncertainty_score":0.07936215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05449105503919781,"score_gpt":0.3589244139169077,"score_spread":0.3044333588777099,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}